{"slug": "meta-unveils-new-tech-that-uses-ai-to-translate-brain-activity-into-text-without", "title": "Meta Unveils New Tech That Uses AI to Translate Brain Activity Into Text—Without Surgery", "summary": "Meta unveiled Brain2Qwerty v2, a non-invasive AI system that translates brain activity into text with 61% average word accuracy, compared to 8% for previous non-invasive methods. The system uses a magnetoencephalography scanner and end-to-end deep learning to decode neural signals, aiming to help people with communication loss due to brain lesions. Meta released the training code and dataset as part of its Digital Brain Project.", "body_md": "#### In brief\n\n- Meta introduced Brain2Qwerty v2, a non-invasive AI system that decodes brain activity into text.\n- The model achieved 61% average word accuracy, compared with about 8% for previous non-invasive methods.\n- Meta released the training code for Brain2Qwerty v1 and v2, while its research partner is releasing the v1 dataset.\n\nMeta on Monday introduced [Brain2Qwerty v2](https://ai.meta.com/blog/brain2qwerty-brain-ai-human-communication/), an AI system that translates brain activity into text using non-invasive brain recordings. The company said the research is intended to help people who have lost the ability to communicate because of brain lesions.\n\nThe system records brain activity using a helmet-like magnetoencephalography (MEG) scanner, a non-invasive brain imaging device commonly used in neuroscience research. It then feeds those raw neural signals into an end-to-end AI model that reconstructs the sentences a person is trying to type. Meta said it further improves accuracy by fine-tuning large language models on neural data, allowing the system to use semantic context when interpreting noisy brain recordings.\n\n“We trained Brain2Qwerty v2 on approximately 22,000 sentences from nine volunteer participants, each recorded for 10 hours wearing a magnetoencephalography (MEG) device while actively typing,” Meta wrote. “Instead of relying on hand-crafted pipelines to detect neural events, we use end-to-end deep learning to decode directly from raw brain signals.”\n\nMeta said Brain2Qwerty achieved a 61% average word accuracy, compared with roughly 8% for previous non-invasive methods. The company is releasing the system's code and dataset as part of its Digital Brain Project, which also includes a $5 million fund to support open neuroscience datasets.\n\nMeta also said decoding accuracy improved as the amount of training data increased, suggesting additional data could further improve performance. The company said [AI agents](https://decrypt.co/resources/what-are-ai-agents-how-autonomous-programs-are-transforming-cryptocurrency) explored possible optimizations for the decoding pipeline before engineers selected the final training configuration.\n\nIn an accompanying [paper](https://www.nature.com/articles/s41593-026-02303-2) published in Nature Neuroscience, Meta researchers argued that while AI has significantly improved brain-to-text decoding, most high-performing brain-computer interfaces still depend on surgically implanted electrodes, making them difficult to scale because of the risks tied to brain surgery and the challenges of [maintaining](https://decrypt.co/230021/neuralink-implant-patient-gaming-sets-bci-record) implants over time.\n\nMeta said Brain2Qwerty v2 approaches levels of accuracy previously achieved only with techniques requiring brain surgery. The company said its non-invasive approach could help bridge the gap between invasive neuroprosthetics and communication systems that do not require surgery.\n\n“Our hope is that this work, done in the open, advances neuroscience to identify, diagnose, and treat neurological disorders faster than in siloes,” Meta wrote.\n\nThe announcement comes as brain-computer interface [research](https://decrypt.co/341655/why-billionaires-betting-brain-computer-interfaces) accelerates, including by Elon Musk’s Neuralink and Merge Labs, backed by OpenAI CEO Sam Altman, developing technology to help restore communication for people with neurological disorders.\n\nWhile companies such as [Neuralink](https://decrypt.co/245875/neuralink-update-alex-counterstrike-cad-software-brain-implant) and [Synchron](https://decrypt.co/249703/new-brain-implant-allows-man-with-als-to-control-alexa-with-his-mind) are pursuing implanted interfaces that require surgery, a growing number of researchers and startups are using AI to improve the performance of non-invasive systems. In September 2024, startup [Neurable](https://decrypt.co/251079/neurables-headphones-track-brain-activity-improve-focus-fight-burnout) introduced AI-powered EEG headphones designed to monitor focus and cognitive fatigue. A year later, MIT spinout [AlterEgo](https://decrypt.co/338527/near-telepathic-wearable-communicate-silently-devices) unveiled a wearable that converts silent neuromuscular signals from the face and throat into text and commands, positioning it as a practical alternative to implanted brain-computer interfaces.\n\nMeta did not immediately respond to a request for comment by *Decrypt.*", "url": "https://wpnews.pro/news/meta-unveils-new-tech-that-uses-ai-to-translate-brain-activity-into-text-without", "canonical_source": "https://decrypt.co/372338/meta-brain2qwerty-ai-brain-activity-text", "published_at": "2026-06-29 18:47:41+00:00", "updated_at": "2026-06-29 19:01:31.786377+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-ethics"], "entities": ["Meta", "Brain2Qwerty", "Nature Neuroscience", "Neuralink", "Synchron", "Neurable", "Merge Labs", "Sam Altman"], "alternates": {"html": "https://wpnews.pro/news/meta-unveils-new-tech-that-uses-ai-to-translate-brain-activity-into-text-without", "markdown": "https://wpnews.pro/news/meta-unveils-new-tech-that-uses-ai-to-translate-brain-activity-into-text-without.md", "text": "https://wpnews.pro/news/meta-unveils-new-tech-that-uses-ai-to-translate-brain-activity-into-text-without.txt", "jsonld": "https://wpnews.pro/news/meta-unveils-new-tech-that-uses-ai-to-translate-brain-activity-into-text-without.jsonld"}}